Chebyshev Inequality with Estimated Mean and Variance

Chebyshev's inequality is investigated when the population mean and variance are estimated from a sample. The necessary modification to the inequality is simple and is actually valid when (a) the population moments do not exist and (b) the sample is exchangeably distributed. The latter case would include, for example, a sample taken without replacement from a finite population and the independent and identically distributed case.     

Mean-Squared errors of small area estimators under a multivariate linear model for repeated measures data

In this paper, we discuss the derivation of the first and second moments for the proposed small area estimators under a multivariate linear model for repeated measures data. The aim is to use these moments to estimate the mean-squared errors (MSE) for the predicted small area means as a measure of precision. At the first stage, we derive the MSE when the covariance matrices are known. At the second stage, a method based on parametric bootstrap is proposed for bias correction and for prediction error that reflects the uncertainty when the unknown covariance is replaced by its suitable estimator.     

Parameter estimation of the generalized Pareto distribution—Part I

The generalized Pareto distribution (GPD) has been widely used in the extreme value framework. The success of the GPD when applied to real data sets depends substantially on the parameter estimation process. Several methods exist in the literature for estimating the GPD parameters. Mostly, the estimation is performed by maximum likelihood (ML). Alternatively, the probability weighted moments (PWM) and the method of moments (MOM) are often used, especially when the sample sizes are small. Although these three approaches are the most common and quite useful in many situations, their extensive use is also due to the lack of knowledge about other estimation methods. Actually, many other methods, besides the ones mentioned above, exist in the extreme value and hydrological literatures and as such are not widely known to practitioners in other areas. This paper is the first one of two papers that aim to fill in this gap. We shall extensively review some of the methods used for estimating the GPD parameters, focusing on those that can be applied in practical situations in a quite simple and straightforward manner.     

Bounds for the expected value of records from discrete distributions

It is well known that under appropriate hypothesis of existence of moments, the expected value of standardized records from continuous distributions are bounded. We show that in the discrete case these quantities may be unbounded. Nevertheless, it is possible to find upper bounds when weak records are considered rather than ordinary ones. We study the particular case of the first standardized spacing.     

Interdistributional Income Inequality

Incomplete moments are used to characterize income inequality and provide the basis for interdistributional Lorenz curves. Four measures of interdistributional inequality are considered and seen to be related to an interdistributional welfare interpretation. Based upon these measures, there has been a significant secular decline in interdistributional inequality between blacks and whites over the past 30 years.     

Effect on probabilities and quantiles of adding a quantity with small variance

This paper gives simple approximations for the distribution function and quantiles of the sum X + Y when X is a continuous variable and Y is an independent variable with variance small compared to that of X . The approximations are based around the distribution function or quantiles of X and require only the first two or three moments of Y to be known. Example evaluations with X having a normal, Student's t or chi-squared distribution suggest that the approximations are good in unbounded tail regions when the ratio of variances is less than 0.2.     

Detection of a change point with local polynomial fits for the random design case

Regression functions may have a change or discontinuity point in the ν th derivative function at an unknown location. This paper considers a method of estimating the location and the jump size of the change point based on the local polynomial fits with one‐sided kernels when the design points are random. It shows that the estimator of the location of the change point achieves the rate n^?1/(2ν+1) when ν is even. On the other hand, when ν is odd, it converges faster than the rate n^?1/(2ν+1) due to a property of one‐sided kernels. Computer simulation demonstrates the improved performance of the method over the existing ones.     

Generalized Method of Moments Estimation When a Parameter Is on a Boundary

This article establishes the asymptotic distributions of generalized method of moments (GMM) estimators when the true parameter lies on the boundary of the parameter space. The conditions allow the estimator objective function to be nonsmooth and to depend on preliminary estimators. The boundary of the parameter space may be curved and/or kinked. The article discusses three examples: (1) instrumental variables (IV) estimation of a regression model with nonlinear equality and/or inequality restrictions on the parameters; (2) method of simulated moments estimation of a multinomial discrete response model with some random coefficient variances equal to 0, some random effect variances equal to 0, or some measurement error variances equal to 0; and (3) semiparametric least squares estimation of a partially linear regression model with nonlinear equality and/or inequality restrictions on the parameters.     

Unbiased estimation of income inequality

In a previous paper Gastwirth shows that a broad family of measures of inequality can be accurately estimated when the tax data are known in groups (more precisely, when we know the number of returns in each of several class intervals and their corresponding average income). In the present paper we show that some measures of the preceding family can be unbiasedly estimated when the tax data are individually known for a sample from the population. Specifically, we construct unbiased estimators of a particular measure of inequality in the samplings with and without replacement, and in the stratified samplings with and without replacement.     

Study of the quality of several asymptotic and near-exact approximations based on moments for the distribution of the Wilks Lambda statistic

In this paper a measure of proximity of distributions, when moments are known, is proposed. Based on cases where the exact distribution is known, evidence is given that the proposed measure is accurate to evaluate the proximity of quantiles (exact vs. approximated). The measure may be applied to compare asymptotic and near-exact approximations to distributions, in situations where although being known the exact moments, the exact distribution is not known or the expression for its probability density function is not known or too complicated to handle. In this paper the measure is applied to compare newly proposed asymptotic and near-exact approximations to the distribution of the Wilks Lambda statistic when both groups of variables have an odd number of variables. This measure is also applied to the study of several cases of telescopic near-exact approximations to the exact distribution of the Wilks Lambda statistic based on mixtures of generalized near-integer gamma distributions.     

Two-sided tests for change in level for correlated data

The classical problem of change point is considered when the data are assumed to be correlated. The nuisance parameters in the model are the initial level μ and the common variance σ². The four cases, based on none, one, and both of the parameters are known are considered. Likelihood ratio tests are obtained for testing hypotheses regarding the change in level, δ, in each case. Following Henderson (1986), a Bayesian test is obtained for the two sided alternative. Under the Bayesian set up, a locally most powerful unbiased test is derived for the case μ=0 and σ²=1. The exact null distribution function of the Bayesian test statistic is given an integral representation. Methods to obtain exact and approximate critical values are indicated.     

Order statistics from discrete distributions

Several recurrence relations and identities available for single and product moments of order1 statistics in a sample size n from an arbitrary continuous distribution are extended for the discrete case,, Making use of these recurrence relations it is shown that it is sufficient to evaluate just two single moments and (n-l)/2 product moments when n is odd and two single moments and {n-2)/2 product moments when n is even, in order to evaluate the first, second and product moments of order statistics in a sample of size n drawn from an arbitrary discrete distribution, given these moments in samples of sizes n-1 and less.. A series representation for the product moments of order statistics is derived.. Besides enabling us to obtain an exact and explicit expression for the product moments of order statistics from the geometric distribution, it. makes the computation of the product moments of order statistics from other discrete distributions easy too.     

Hybrid censoring schemes with exponential failure distribution

The mixture of Type I and Type I1 censoring schemes, called the hybrid censoring, is quite important in life–testing experiments. Epstein(1954, 1960) introduced this testing scheme and proposed a two–sided confidence interval to estimate the mean lifetime, θ, when the underlying lifetime distribution is assumed to be exponential. There are some two–sided confidence intervals and credible intervals proposed by Fairbanks et al. (1982) and Draper and Guttman (1987) respectively. In this paper we obtain the exact two–sided confidence interval of θ following the approach of Chen and Bhattacharya (1988). We also obtain the asymptotic confidence intervals in the Hybrid censoring case. It is important to observe that the results for Type I and Type II censoring schemes can be obtained as particular cases of the Hybrid censoring scheme. We analyze one data set and compare different methods by Monte Carlo simulations.     

On lower bounds for tail probabilities

Chebyshev's inequality and its generalizations make it possible to give upper bounds for the tail probabilities in the distribution of a random variable. We present a method of finding lower bounds for these probabilities . The method is based on improvements of the Lyapunov inequality for moments of a random variable.     

A bivariate distribution with gamma and beta marginals with application to drought data

The first known bivariate distribution with gamma and beta marginals is introduced. Various representations are derived for its joint probability density function (pdf), joint cumulative distribution function (cdf), product moments, conditional pdfs, conditional cdfs, conditional moments, joint moment generating function, joint characteristic function and entropies. The method of maximum likelihood and the method of moments are used to derive the associated estimation procedures as well as the Fisher information matrix, variance–covariance matrix and the profile likelihood confidence intervals. An application to drought data from Nebraska is provided. Some other applications are also discussed. Finally, an extension of the bivariate distribution to the multivariate case is proposed.     

Asymptotic expansions for the moments of serial correlation coefficients

This work is concerned with evaluating the moments of a number of serial correlation coefficients which arise in various ways and where the observations are from the first order autoregressive Gaussian process with known zero mean. The forms considered have biases whose main parts (of order 0(n^-1) , where n is the sample size) are substantially different. They are the intra-class correlation,the maximum likelihood estimators and an estimator whose main part of the bias is sere. The moments are obtained as asymptotic expansions in terms of the parameter of the process and to terms of order 0(n^-3). It is found that removing certain end terms in the denominator of a serial correlation has the effect of reducing the magnitude of the main part of its bias considerably and in one case completely eliminating it. This work extends the results of various authors,e.g.Kandall(1954), Marriott and pope(1954) and white (1961) in the special cases of the first order autogressive process.     

Durbin–Watson and Generalized Durbin–Watson Tests for Autocorrelations and Randomness

The Durbin–Watson (DW) test for lag 1 autocorrelation has been generalized (DWG) to test for autocorrelations at higher lags. This includes the Wallis test for lag 4 autocorrelation. These tests are also applicable to test for the important hypothesis of randomness. It is found that for small sample sizes a normal distribution or a scaled beta distribution by matching the first two moments approximates well the null distribution of the DW and DWG statistics. The approximations seem to be adequate even when the samples are from nonnormal distributions. These approximations require the first two moments of these statistics. The expressions of these moments are derived.     

On asymptotic approximation of inverse moments for a class of nonnegative random variables

Sung [On inverse moments for a class of nonnegative random variables. J Inequal Appl. 2010;2010:1–13. Article ID 823767, doi:10.1155/2010/823767] obtained the asymptotic approximation of inverse moments for a class of nonnegative random variables with finite second moments and satisfying a Rosenthal-type inequality. In the paper, we further study the asymptotic approximation of inverse moments for a class of nonnegative random variables with finite first moments, which generalizes and improves the corresponding ones of Wu et al. [Asymptotic approximation of inverse moments of nonnegative random variables. Statist Probab Lett. 2009;79:1366–1371], Wang et al. [Exponential inequalities and inverse moment for NOD sequence. Statist Probab Lett. 2010;80:452–461; On complete convergence for weighted sums of ? mixing random variables. J Inequal Appl. 2010;2010:1–13, Article ID 372390, doi:10.1155/2010/372390], Sung (2010) and Hu et al. [A note on the inverse moment for the nonnegative random variables. Commun Statist Theory Methods. 2012. Article ID 673677, doi:10.1080/03610926.2012.673677].     

The Poisson Maximum Entropy Model for Homogeneous Poisson Processes

Our main interest is parameter estimation using maximum entropy methods in the prediction of future events for Homogeneous Poisson Processes when the distribution governing the distribution of the parameters is unknown. We intend to use empirical Bayes techniques and the maximum entropy principle to model the prior information. This approach has also been motivated by the success of the gamma prior for this problem, since it is well known that the gamma maximizes Shannon entropy under appropriately chosen constraints. However, as an alternative, we propose here to apply one of the often used methods to estimate the parameters of the maximum entropy prior. It consists of moment matching, that is, maximizing the entropy subject to the constraint that the first two moments equal the empirical ones and we obtain the truncated normal distribution (truncated below at the origin) as a solution. We also use maximum likelihood estimation (MLE) methods to estimate the parameters of the truncated normal distribution for this case. These two solutions, the gamma and the truncated normal, which maximize the entropy under different constraints are tested as to their effectiveness for prediction of future events for homogeneous Poisson processes by measuring their coverage probabilities, the suitably normalized lengths of their prediction intervals and their goodness-of-fit measured by the Kullback–Leibler criterion and a discrepancy measure. The estimators obtained by these methods are compared in an extensive simulation study to each other as well as to the estimators obtained using the completely noninformative Jeffreys’ prior and the usual frequency methods. We also consider the problem of choosing between the two maximum entropy methods proposed here, that is, the gamma prior and the truncated normal prior, estimated both by matching of the first two moments and, by maximum likelihood, when faced with data and we advocate the use of the sample skewness and kurtosis. The methods are also illustrated on two examples: one concerning the occurrence of mammary tumors in laboratory animals taking part in a carcinogenicity experiment and the other, a warranty dataset from the automobile industry.     

Convergence rate for cross-validatory bandwidth in kernel hazard estimation from dependent samples

This paper is devoted to the nonparametric estimation of hazard function by means of kernel smoothers, and more specifically to the crucial problem of bandwidth selection. We first get the convergence rate of usual cross-validated bandwidth under a general dependence assumption on the sample data, extending in several directions the results existing in the literature. In a second attempt, this rate of convergence is used to motivate the introduction of a penalized version of the cross-validation procedure. The rate of convergence is calculated, and a short simulation study, together with a practical application to real data, shows the interest of this approach for finite sample studies. Finally, as a by-product of our proofs, we state a general inequality for the moments of sums of strong dependent variables. Because of its possible interest for many other purposes apart from hazard estimation, this inequality is presented in a specific self-contained section.